The Gap Between a Helpful Assistant and a Senior Engineerblog.ezyang.com2 points·by tim_sw·6 เดือนที่ผ่านมา·0 comments
VLLM: Anatomy of a High-Throughput LLM Inference Systemaleksagordic.com4 points·by tim_sw·11 เดือนที่ผ่านมา·1 comments
DeepSeek: Inference-Time Scaling for Generalist Reward Modelingarxiv.org163 points·by tim_sw·ปีที่แล้ว·35 comments
AI forecasting retrospective: you're (probably) over-confidentnicholas.carlini.com3 points·by tim_sw·ปีที่แล้ว·0 comments
Will Scaling Reasoning Models Like O3 and R1 Unlock Superhuman Reasoning?scaling-reasoning.chrisbarber.co4 points·by tim_sw·ปีที่แล้ว·0 comments
The Online Sports Gambling Experiment Has Failedlesswrong.com8 points·by tim_sw·2 ปีที่แล้ว·1 comments
Interview with Andrew Kelley (Zig Creator) (2021)corecursive.com111 points·by tim_sw·3 ปีที่แล้ว·23 comments